Sign in Subscribe

benchmarks

Everything tagged benchmarks.

Share your story Subscribe

Featured

Microsoft releases ThinkingBox agent benchmark through Hugging Face

Microsoft releases ThinkingBox agent benchmark through Hugging Face

DP News TeamOct 4, 2026

Perplexity releases Q2D-Web benchmark for web-scale retrievers

Perplexity releases Q2D-Web benchmark for web-scale retrievers

Hugging Face releases 207 WebGPU kernels for local AI

Hugging Face releases 207 WebGPU kernels for local AI

Latest

News
OpenAI publishes first Jalapeño inference chip benchmarks
OpenAI reported that Jalapeño, its first custom inference chip, delivered up to 1.9 times more AI work per watt and up to 3.6 times lower end-to-end…
DP News Team · Sep 2
News
xAI ships Grok 4.6, a post-training-only upgrade it says matches GPT-5.6 Sol
xAI released Grok 4.6 on August 12, 2026, a post-training-only upgrade whose Artificial Analysis Intelligence Index score of 61 the company says…
DP News Team · Aug 12
News
Upstage releases Solar Pro 4, tripling its Artificial Analysis Intelligence Index score
South Korean lab Upstage released Solar Pro 4, which tracker Artificial Analysis scored 42 on its Intelligence Index, versus 14 for its predecessor.
DP News Team · Aug 11
News
Fable 5 tops Cursor's CursorBench 3.1 coding-agent leaderboard as the vendor eval resurfaces
On Cursor's vendor-run CursorBench 3.1 leaderboard, Fable 5 Max scores 72.9% at $18.02 per task, leading 36 tracked model configurations.
Dmytro Spodarets · Jul 3